Related papers: SetupX: Can LLM Agents Learn from Past Failures in…
Automated testing for REST APIs has become essential for ensuring the correctness and reliability of modern web services. While existing approaches primarily focus on detecting server crashes and error codes, they often overlook logical…
The ability to detect and analyze failed executions automatically is crucial for an explainable and robust robotic system. Recently, Large Language Models (LLMs) have demonstrated strong reasoning abilities on textual inputs. To leverage…
Recent research has turned to Reinforcement Learning (RL) to solve challenging decision problems, as an alternative to hand-tuned heuristics. RL can learn good policies without the need for modeling the environment's dynamics. Despite this…
As a codebase expands over time, its library dependencies can become outdated and require updates to maintain innovation and security. However, updating a library can introduce breaking changes in the code, necessitating significant…
Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validation. Under this evaluation setting, success is determined…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
Function-level code generation leverages foundation Large Language Models (LLMs) to automatically produce source code with expected functionality. It has been widely investigated and applied in intelligent programming assistants, such as…
We present MemX, a local-first long-term memory system for AI assistants with stability-oriented retrieval design. MemX is implemented in Rust on top of libSQL and an OpenAI-compatible embedding API, providing persistent, searchable, and…
In real-world software engineering tasks, solving a problem often requires understanding and modifying multiple functions, classes, and files across a large codebase. Therefore, on the repository level, it is crucial to extract the relevant…
Many cloud services provide REST API accessible to client applications. However, developers often identify specification violations only during testing, as error messages typically lack the detail necessary for effective diagnosis.…
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…
As Large Language Models (LLMs) show their capabilities across various applications, training customized LLMs has become essential for modern enterprises. However, due to the complexity of LLM training, which requires massive computational…
The rapid advancement of large language models (LLMs) demands robust, unbiased, and scalable evaluation methods. However, human annotations are costly to scale, model-based evaluations are susceptible to stylistic biases, and…
Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static target and struggle to reconfigure behavior on demand.…
In recent years, large language models (LLMs) have made significant progress in code intelligence, yet systematically evaluating their code understanding and reasoning abilities remains challenging. Mainstream benchmarks such as HumanEval…
Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workflows faces two obstacles: the lack of environments supporting…
Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce…
Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging and safety-critical scenarios. However, existing scenario…
As REST APIs become an increasingly significant part of software systems, their validation is becoming more critical. Hence, testing and uncovering underlying issues are of utmost importance for improving software quality. However, testing…
Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models…